© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 53232
    Prev
    Next
    INDEX
    Explanations

    times, dates, or durations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    adamkarvonen/qwen3-32b-saes/saes_Qwen_Qwen3-32B_batch_top_k/resid_post_layer_32
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ä½Ĩä¸įéĻIJäºİ
    -0.09
    anto
    -0.09
    phans
    -0.09
    uly
    -0.08
    ici
    -0.08
    æı©
    -0.07
    ovie
    -0.07
    ality
    -0.07
    idon
    -0.07
    cale
    -0.07
    POSITIVE LOGITS
     Champ
    0.09
    ADVERTISEMENT
    0.09
    çĹķ
    0.08
    VN
    0.08
    çijķ
    0.08
    è¿Ļå¥Ĺ
    0.08
    ORLD
    0.08
    妹
    0.08
    ä¸Ģå°ı
    0.08
    èĥ
    0.08
    Activations Density 0.066%

    No Known Activations